Individual Project 2 - Rust micro-server for Text Summarization

This project aims to build a Rust micro-server that summarizes text, based on the common task of reading and summarizing books among students. The project uses the rust actix and libtorch to run a pre-trained hugging-face model for summarization.

Project Goals/Outcomes

• Develop my Rust micro-service with kubernetes
• Use Github Codespaces and Copilot
• Integrate libtorch and 'hugging-face pretrained models' into a Rust web project

Architectural Diagram

Demo

• https://apiv2.sszzz.me

Kubernetes Deployment

• go to the directory K8s

cd K8s

• create the namespace resume-prod

kubectl create namespace resume-prod

• apply the yaml files

kubectl apply -f .

Docker(Recommended)

• This repo main branch is automatically published to Dockerhub with CI/CD, you can pull the image from here

docker pull szheng3/sz-rust-ml:latest

• Run the docker image.

docker run -d -p 8000:8000 szheng3/sz-rust-ml:latest

Setup Manually

1. Install rust via rustup
2. Install the libtorch (for Mac M1), Intel chips users can skip this step
3. node

brew install pytorch@1.13.1

Not Mac ARM chips users

• Build frontend

make frontend 

• Run, you can run the rust web app.

make run 

• Release

make releasex86

• Bench

make benchx86

Mac ARM chips users

• Build frontend

make frontend 

• change the path in the Makefile to your libtorch path

export LIBTORCH=/opt/homebrew/Cellar/pytorch/1.13.1 &&export LD_LIBRARY_PATH=${LIBTORCH}/lib:$LD_LIBRARY_PATH

• Run, you can run the rust web app.

make runarm 

• Release

make release

• Bench

make bench

CI/CD

Github Actions configured in .github/workflows

GitHub releases

The binary could be downloaded from the release pages. release

Benchmark Results

Logging

Progress Log

• Configure Github Codespaces.
• Initialise Rust project with pretrained model from hugging-face
• CI/CD with Github Actions
• Tag and Releases
• Benchmark
• kubernetes deployment
• logging

References

• rust-cli-template
• rust-bert